|Publication number||US7392472 B2|
|Application number||US 10/133,939|
|Publication date||Jun 24, 2008|
|Filing date||Apr 25, 2002|
|Priority date||Apr 25, 2002|
|Also published as||DE60322999D1, EP1357508A2, EP1357508A3, EP1357508B1, US20030204816|
|Publication number||10133939, 133939, US 7392472 B2, US 7392472B2, US-B2-7392472, US7392472 B2, US7392472B2|
|Inventors||Patrice Y. Simard, James Russell Rinker|
|Original Assignee||Microsoft Corporation|
|Export Citation||BiBTeX, EndNote, RefMan|
|Patent Citations (100), Non-Patent Citations (30), Referenced by (11), Classifications (6), Legal Events (3)|
|External Links: USPTO, USPTO Assignment, Espacenet|
The present invention relates generally to document image processing, and more particularly to a system and method facilitating layout analysis.
The amount of information available via computers has dramatically increased with the wide spread proliferation of computer networks, the Internet and digital storage means. With such increased amount of information has come the need to transmit information quickly and to store the information efficiently.
Textual documents are often kept or transmitted in bitmap form (e.g., fax, paper, or bitmaps). In such form, the text cannot be easily extracted, searched, re-flowed, cut and pasted, re-purposed, or compressed, because it is not known a priori which pixels should be interpreted as text, background, image, or just noise.
There is, therefore, a need to recover structure, such as words, lines, and paragraphs and blocks from the pixel representation of a document. The indiscriminate pixels can be referred as “dead bits”, and the task is to recover the “live” structure of the document. The recovered structure can be used to locate the good candidate for textual characters and, thus, can facilitate optical character recognition (OCR). The textual structure can also help text selection for features such as “cut & paste”. Similarly, the textual structure can give hint(s) about how to insert and reflow text (e.g., reflow only the current paragraph while moving the next paragraphs as whole). Finally, the structure can help compression greatly by predicting the position of characters with respect to their current line, or block.
Additionally, data compression of digital documents should make use of an intended purpose or ultimate use of a document. Some digital documents are employed for filing or providing hard copies. Other documents may be revised and/or edited. Many conventional data compression methodologies fail to handle re-flowing of text and/or images when viewed, and fail to provide efficient and effective means to enable compression technology to recognized characters and re-flow them to word processors, personal digital assistants (PDAs), cellular phones, and the like. Therefore, if hard copy office documents are scanned into digital form, current compression technology can make it difficult, if not impossible, to update, amend, or in general change the digitized document.
The following presents a simplified summary of the invention in order to provide a basic understanding of some aspects of the invention. This summary is not an extensive overview of the invention. It is not intended to identify key/critical elements of the invention or to delineate the scope of the invention. Its sole purpose is to present some concepts of the invention in a simplified form as a prelude to the more detailed description that is presented later.
The present invention provides for a layout analyzer that receives connected component information. The connected component information can include color, vertical position, horizontal position, height (e.g., y size) and/or width (e.g., x size) of connected component(s). The connected component information can be related to an image input (e.g., based on a document to be archived and/or transmitted). The image input can be a document image (e.g., a binary, RGB and/or YUV representation of document(s)). The connected component information can be based, at least in part, upon a binary representation associated with the image input. Such binary representation can be obtained via thresholding, or via more complex binarization method. For instance, some technologies separate a color image into a foreground and a background, with a binary image which indicate for each pixel whether the pixel belongs to the foreground or the background. The binary image, sometimes referred as a mask, is generally intended to capture text, lines, graphic art and/or many other sharp contrast component.
The layout analyzer can output layout information to be used, for example, by an encoder to enable OCR, cut & paste, data compression, etc. The layout information can further enable reflow of connected component(s) on an output device, such as, a computer display, PDA, text-enabled mobile telephone and/or text-enabled pager.
The invention can be explained in terms of operations on connected components; however, it should be understood that in some case, some connected components can be can be separated, while yet other connected components can be joined, and the result is still identified as connected components. For instance, the letter “p” from a line, may touch a “t” from the line below, because of pixel noise, smirring, or as a result of a particularly artistic font. The combined letter would then be an unusually large connected component. It is possible that during the layout analysis performed on connected component (CC), that particular connected component can be identified as an outlier (using OCR for instance) and consequently broken into two or more pieces. Even though the two pieces would still be touching, they can be identified as two connected components. Similarly, the letter “i” is composed of two distinct connected components, but as the layout analysis progresses, it is fairly easy to detect that they form a single letter and can advantageously be considered as one unique entity, which can be identified as a connected component.
In what follows, we will use the term joining of connected components not in the sense of creating another “connected component”, but rather, connected component will be grouped (or joined) into “words”. Similarly, words will be joined into lines, and lines will be joined to form blocks (e.g., paragraphs).
The layout analyzer includes a CCs to word component and a words to line component. The CCs to word component includes a CC organizer that is adapted to organize connected component(s) by color, vertical position and/or horizontal position. The CCs to word component further includes a CC joiner adapted to join connected components based, at least in part, upon color, vertical position, horizontal position, join distance (e.g., distance between the connected components), height of the connected components and/or width of the connected components. Joined connected components can include two or more connected components and form a word.
The words to line component includes a word organizer adapted to organize words by at least one of color, vertical position, horizontal position, and length and a word joiner, adapted to join words into line, based at least in part on vertical position, horizontal position, join distance, and statistics collected over the words to be joined, such as word angle, median height, median width of connected components composing the words.
Therefore, layout analysis of the layout analyzer can be decomposed in at least two processes: The process of joining connected components into words by the CC joiner, and the process of joining words into lines by the word joiner of the words to line component.
Another aspect of the present invention provides for a layout analyzer to optionally further include a third process—joining lines into blocks by a lines to block component. The lines to block component includes a line organizer and a line joiner.
The line organizer is adapted to organize lines by color, vertical position, horizontal position, and/or length. The line joiner merges lines (comprising previously merged words) into a block. Merging of the line joiner can be similar to the CC joiner and/or the word joiner. The line joiner can proceed by taking a pair of lines and subjecting them to a series of test(s). For example, the test(s) can compare the median widths, the median heights, the angles of each line and/or their respective positions. In one example, the line joiner utilizes a vertical overlap test. For vertical joining, two lines have a vertical overlap (e.g., one is partially above the other). For example, the vertical overlap can be controlled by a threshold, multiplied by the median width of the longest line. The threshold can be a function of the length of the line, meaning that the test might fail at first, but succeed later, when more statistics have been gathered.
When words are joined into lines by the word joiner, line statistics are recomputed. When lines are joined into blocks by a line joiner, block statistics are recomputed. Since connected component(s) have access to word(s) it/they belong to, and the word(s) have access to the line(s) it/they belong to, and the line(s) have access o the block(s) it/they belong too, in one example, substantially each entity (e.g., CC, word, line) to have access to the statistics of the largest enclosing entity, all the way to the blocks if blocks have been made. Because the statistics can change for each joining entity operation (e.g., CC joiner, word joiner and/or line joiner), other joining attempts over children of these entities (which have previously failed) can be revisited and might succeed.
Yet another aspect of the present invention provides for a layout analysis system having a layout analyzer and a connected component store. The connected component store stores information associated with a plurality of connected components, such as, width (e.g., x size), height (e.g., y size), color, horizontal position (e.g., absolute and/or relative) and/or vertical position (e.g., absolute and/or relative) of the plurality of connected components.
Another aspect of the present invention provides for the layout analyzer to be employed in a vast array of document image applications, including, but not limited to, segmented layered image systems, photocopiers, document scanners, optical character recognition systems, personal digital assistants, fax machines, digital cameras, tablet personal computers and/or digital video cameras.
Other aspects of the present invention provide methods for layout analysis, a computer readable medium having computer usable instructions for a system for layout analysis, a computer readable medium storing computer executable instructions operable to perform a method for layout analysis and a data packet adapted to be transmitted between two or more computer processes comprising information associated with layout information, the layout information comprising at two joined connected components, joining being based, at least in part, upon at least one of color, vertical position, horizontal position, a distance between the connected components, height of the connected components and width of the connected components.
To the accomplishment of the foregoing and related ends, certain illustrative aspects of the invention are described herein in connection with the following description and the annexed drawings. These aspects are indicative, however, of but a few of the various ways in which the principles of the invention may be employed and the present invention is intended to include all such aspects and their equivalents. Other advantages and novel features of the invention may become apparent from the following detailed description of the invention when considered in conjunction with the drawings.
The present invention is now described with reference to the drawings, wherein like reference numerals are used to refer to like elements throughout. In the following description, for purposes of explanation, numerous specific details are set forth in order to provide a thorough understanding of the present invention. It may be evident, however, that the present invention may be practiced without these specific details. In other instances, well-known structures and devices are shown in block diagram form in order to facilitate describing the present invention.
As used in this application, the terms “computer component” is intended to refer to a computer-related entity, either hardware, a combination of hardware and software, software, or software in execution. For example, a computer component may be, but is not limited to being, a process running on a processor, a processor, an object, an executable, a thread of execution, a program, and/or a computer. By way of illustration, both an application running on a server and the server can be a computer component. One or more computer components may reside within a process and/or thread of execution and a component may be localized on one computer and/or distributed between two or more computers.
Further, “document image” is intended to refer to a digital representation of document(s) comprising one or more color(s) (e.g., binary (e.g., black/white), gray-scale and/or color document(s)). Additionally, a document image can have image(s), text and/or text with images. A document image can be binary, RGB and/or YUV representations of document(s). An RGB document image is represented by red, green and blue components. A YUV document image is represented using a luminescence component denoted by Y and chrominance components denoted by U and V. Less bits can be used to represent the chrominance components U and V without significantly sacrificing visual quality of the YUV image. The YUV representation is, generally, a more compact and easy to use representation than an RGB representation. A document image comprises picture elements commonly referred to as “pixels”. A document image can be based on single or multi-page document(s) of any shape or size.
The layout analyzer 100 receives connected component information. A “connected component” refers to a set of pixels of a given color that are connected (e.g., having 4-connectivity and/or 8-connectivity). Referring briefly to
Each connected component has associated information which can include color, vertical position, horizontal position, height (e.g., y size) and/or width (e.g., x size) of connected component(s). The connected component information can be computed effectively from an image using a connected component extractor (not shown) and can be related to an image input (e.g., based on a document to be archived and/or transmitted). For example, the image input can be a document image (e.g. a binary, RGB and/or YUV representation of document(s)). The connected component information can be based, at least in part, upon a binary representation associated with the image input. Such binary representation can be obtained via thresholding, or via more complex binarization method. For instance, some technologies separate a color image into a foreground and a background, with a binary image which indicate for each pixel whether the pixel belongs to the foreground or the background. The binary image, sometimes referred as mask, is generally intended to capture text, lines, graphic art and/or many other sharp contrast component(s).
Turning back to
The CCs to word component 110 facilitates organization and joining of connected components into a word. As used in this application, a “word” refers to a group of connected components which are within physical proximity to each other and can include letter(s), number(s) and/or punctuation mark(s); and, as such, as used in this application “word” is not limited to grammatical words.
The CC organizer 130 receives connected component information and organizes (e.g., sorts) connected component(s) by color, vertical position and/or horizontal position. The CC organizer 130 can effectively limit the number of pair of connected component which are compared in order to join them into word. In one example, the CC organizer 130 can sort the connected components according to vertical positions, and only consider the pairs of connected components that are sufficiently close—with some vertical overlap, as candidate for being adjacent in a word. In another example, the CC organizer 130 can limit the number of comparison even more by taking into account the two dimensional layout of the connected component and only compare those that are within a short distance. In yet another example, the CC organizer 130 sorts the connected components based on color, vertical position and then horizontal position. Each connected component is then considered for joining in order. A join distance can be calculated for the connected component of focus. For example, the join distance can initially be calculated as a percentage (e.g., 50 percent) of the focus connected component width; however, in the instance where the join distance is less than a percentage (e.g., 33 percent) of the focus connected component height, the join distance can be calculated as a percentage (e.g., 50 percent) of the focus connected component height.
Referring briefly to
The data structure 400 is merely exemplary and it is to be appreciated that numerous other structures are contemplated that provide for organizing and/or storing a plurality of data types conducive to facilitating layout analysis in connection with the subject invention. Any such data structure suitable for employment in connection with the present invention is intended to fall within the scope of the appended claims. Such data structures can be stored in computer readable media including, but not limited to, memories and, disks.
Referring back to
Turning briefly to
Referring back to
In one example, the CC joiner 140 performs a series of tests which must all succeed for two connected components to be considered as adjacent CCs of the same word. The tests are based on the sizes and positions of the bounding boxes, and can also use statistics gathered over previously joined connected component. For instance a first test is based on the bottom right of the bounding box of a first connected component is to the left and a threshold (e.g., 0.5) times the width of the second connected component. A second test is based on the vertical position of the same bottom right of first bounding box is comprised between the top and bottom position of bounding box of second component. Note that the second test is scale invariant, in the sense that if the image is scaled up or down, the result of the test is unchanged. A third test is based on the width ratio between first and second connected component be comprise between a second and third threshold. To prevent oddities due to very skinny letters such as “1” or “1”, it can be advantageous to replace the true width by a minimum width, which can be set, for instance, as the largest value of the true width, and half the height. A similar test can be constructed for the ratio of heights between connected components. More robust tests can be made by comparing the width of a connected component with the median width of the word assembled so far for the second connected component. The median is considered more robust than the average because the median is much less sensitive to outliers in the data. As the word is assembled, the median is computed over a larger sample, and becomes a more reliable estimate of the width. A similar and symmetric test can be done by comparing the width of the second connected component with the median width of the word containing the first connected component. If words have been assembled into lines, or into blocks, the median width of the line or of the block can be used for an even better estimate of the font's width. As these estimate become more and more accurate, the tests used by the joiner can be more aggressive. This means that the tests are a function of the number of components that have been previously joined. At the beginning, the tests are very conservative, but as few connected components are joined, it enables other connected component to be joined as well. In effect, connected components “condense” around the places where the joining is easiest and less ambiguous. The above description was made for widths, but clearly, similar tests can be used to compare heights, and median heights. Other tests can involve more than a pair of CC, because when a pair is considered, the CCs belonging to word (parents) of each CC can also be examined.
Referring briefly to
Turning back to
In comparing relative size(s) of the connected component(s) with the focus-connected component, bounding boxes (width and height) of the connected component(s) and the focus-connected component can be utilized. For example, if (1) the height of a connected component is within a first height range (e.g., about 50 percent to 200 percent) of the height of the focus connected component; and, (2) the width of the connected component is within a width range (e.g., about 12 percent to about 800 percent) of the width of the focus connected component, the connected component can be further considered for joining with the focus connected component; otherwise, the connected component is not joined with the focus connected component.
One such further consideration can be a second height comparison of the connected component with the focus connected component. The second and later comparison may be prompted by the gathering of further information resulting from either additional merges of CCs into a word, additional merges of words into a line, or additional merges of lines into a block. For example, if the height of the connected component is within a second height range (e.g., about 90 percent to 110 percent) of the median height of all the CCs of the group containing the focus CC, the connected component can be joined with the focus connected component (e.g., into a “word”). Alternatively, the median height of the connected components of the group containing the connected component can be compared with either the height of the focus connected component, or with the median height of the CCs of the group containing the focus connected component. If the second height comparison is unsuccessful, a second further consideration can be based on a calculated join distance for the connected component. The join distance can be calculated as described previously with respect to join distance of the focus connected component. If the focus connected component falls within the join distance of the connected component, the connected component can be joined with the focus connected component.
Typically, the further comparisons can be more “relaxed” because they involve statistics that are more reliable, since they have been collected over a larger sample of data. For instance, it is possible that the initial threshold may prevent the joining of CCs into a long word because of a badly distorted letter, e.g., CC, in the middle. But after the two half of the word have been assembled, the median heights and median width of the two half of the word may match very well, and consequently, the threshold of the merge between the two CCs that would not initially join can be relaxed to allow the merge on one of the subsequent tries.
Joined connected components can include two or more connected components. Once substantially all of the connected component have been attempted to be joined, the CC joiner 140 can successively attempt to further join the joined connected components. Statistics for use by the CC joiner 140 (e.g., width and/or height) can be based on the joined connected components. When a pair of CCs passes substantially all the tests, the connected components are joined by the CC joiner 140 and made element of the same word. When this happens, the statistics of the word (for instance, the median width or height) can be recomputed.
As described earlier, the process of joining CCs by the CC joiner 140 enables CCs to have access to more robust statistics by looking for quantities collected over the set (e.g., word, line, block) to which they belong. The new statistics, enables more aggressive tests to be performed.
The word organizer 150 is adapted to organize words by color, vertical position, horizontal position, and/or length. The word joiner 160 of the words to line component 120 similarly attempts to merge words (previously merged by the CC joiner 140) into a line. The word joiner 160 can employ tests similar to those explained previously with regard to the CC joiner 140. However, optionally, the word joiner 160 can employ additional test(s). For example, the word joiner 160 can include a line regression for each word and/or a test for word alignment.
Therefore, layout analysis of the layout analyzer 100 can be decomposed in at least two processes: The process of joining connected components into words by the CC joiner 140, and the process of joining words into lines by the word joiner 160 of the words to line component 120. Referring briefly to
The line organizer 180 is adapted to organize lines by color, vertical position, horizontal position, and/or length. The line joiner 190 merges lines (comprising previously merged words) into a block. Merging of the line joiner 190 can be similar to the CC joiner 140 and/or the word joiner 160. The line joiner 190 can proceed by taking a pair of lines and subjecting them to a series of test(s). For example, the test(s) can compare the median widths, the median heights, the angles of each line and/or their respective positions. In one example, the line joiner 190 utilizes a vertical overlap test. For vertical joining, two lines must have a vertical overlap (e.g., one is partially above the other). For example, the vertical overlap can be controlled by a threshold, multiplied by the median width of the longest line. The threshold can be a function of the length of the line, meaning that the test might fail at first, but succeed later, when more statistics have been gathered.
When words are joined into lines by the word joiner 160, line statistics are recomputed. When lines are joined into blocks by a line joiner 190, block statistics are recomputed. Since each connected component has access to the word it belong to, and each word has access to the line it belong to, and each line has access to the block it belong too, in one example, substantially each entity (e.g., CC, word, line) to have access to the statistics of the largest enclosing entity, all the way to the blocks if blocks have been made. Because the statistics can change for each joining entity operation (e.g., CC joiner 140, word joiner 160 and/or line joiner 190), other joining attempts over children of these entities (which have previously failed) can be revisited and might succeed.
Accordingly, the organizers (CC organizer 130, word organizer 150 and/or line organizer 180) can keep ordered lists of most likely candidate for merges, to effectively attempt the most likely merge first.
When words are merged by the word joiner 160, this can be a signal that new CC merges should be attempted by the CCs to word component 110. Similarly, when lines are merged by the line joiner 190, this can be a signal that new words may be merged by the word joiner 160. The process completes since merges are typically not undone since the initial assumption is that merge(s) are not performed erroneously. For this assumption to be true, merge operation(s) are performed conservatively (e.g., to minimize merging error(s)). The cost of under-merging is just that we end up with more entities in the end. The cost of over-merging is that statistics are corrupted, with potentially disastrous effects.
In one example, in order to keep computations reasonable, several optimizations can be done. For instance, it is possible to first attempt substantially all the CC merges by the CCs to word component 110, then substantially all the word merges by the words to line component 120, followed by the line merges by the lines to block component 170. Thereafter, the process is cycled again (e.g., starting with CC merges by the CCs to word component 110, followed by word merges by the words to line component 120 and followed by the line merges by the lines to block 170, etc.).
In one example, at least one of the organizers, for example, the CC organizer 130, the word organizer 150 and/or the line organizer 180, can also keep a list of substantially all the pairs that are potential merges. For instance each entity can have a list of K (e.g. K=4) entities that are good prospects for merging. Every time a merge occurs, substantially all the entity that are children to this entity can be invalidated, so that these prospect merges are re-tested.
Turning next to
The connected component store 810 stores information associated with a plurality of connected components. For example, the connected component store 810 can store width (e.g., x size), height (e.g., y size), color, horizontal position (e.g., absolute and/or relative) and/or vertical position (e.g., absolute and/or relative) of the plurality of connected components.
The layout analyzer 100 can utilize the information stored in the connected component store 810 in order to perform layout analysis of connected component(s). The layout analyzer 100 is adapted to organize connected component(s) by color, vertical position and/or horizontal position. Thereafter, the layout analyzer 100 is adapted to join connected components based, at least in part, upon color, vertical position, horizontal position, join distance (e.g., distance between the connected components), height of the connected components and/or width of the connected components. The layout analyzer 100 can output layout information to be used, for example, by an encoder to enable data compression. The layout information can further enable reflow of connected component(s) on an output device (not shown) (e.g., computer display, PDA, text-enabled mobile telephone and/or text-enabled pager).
Referring next to
The mask separator 910 receives a document image (e.g., based on a document to be archived and/or transmitted). For example, the segmented layered image system 900 can be part of a document compression system (not shown). The document image can be a binary, RGB and/or YUV representation of document(s). The mask separator component 910 processes the document image and outputs a mask (e.g., binary) indicating whether each pixel of the document image belongs in the foreground and/or background.
The layout analyzer 930 receives information regarding connected components and performs layout analysis of connected components. The layout analyzer 930 is adapted to organize connected component(s) by color, vertical position and/or horizontal position. Thereafter, the layout analyzer 930 is adapted to join connected components based, at least in part, upon color, vertical position, horizontal position, join distance (e.g., distance between the connected components), height of the connected components and/or width of the connected components. The layout analyzer 930 can output layout information to be used by the mask encoder 940.
For instance, the layout analyzer provide a logical ordering of the CC, and might greatly help in predicting the positions of each marks. Better position prediction yield better compression.
The mask encoder 940 encodes the mask and/or layout information into mask bits.
It is to be appreciated that the mask separator component 910, the layout analyzer 930 and/or the mask encoder 940 can be computer component(s) as that term is defined herein.
Turning next to
The foreground/background segmenter 1050 receives the mask from the mask separator 1010 and the document image. The foreground background segmenter 1050 uses the mask to generate a foreground image and a background image from the document image. For each pixel of the document image, a corresponding pixel of the mask is referenced. The pixel is allocated to the foreground image or the background image based on that corresponding pixel of the mask. For example, if the corresponding pixel of the mask is a “1”, the pixel is assigned to the foreground image. Conversely, if the corresponding pixel of the mask is a “0”, the pixel is assigned to the background image. It is appreciated that whether a “0” or “1” indicates the foreground or background can vary.
The foreground encoder 1060 receives the foreground image and encodes the foreground image to generate compressed bits or a compressed foreground stream of bits from the foreground image. Any suitable encoding technique can be used for the foreground encoder 1060. For example, progressive wavelength encoding or progressive transform encoding can be used to encode the foreground image.
The background encoder 1070 receives the background image and encodes the background image to generate compressed bits or a compressed background stream of bits from the background image. For example, progressive wavelength encoding or progressive transform encoding can be used to encode the foreground image.
The combiner component 1080 receives the compressed bits from the mask encoder 1040, the foreground encoder 1060 and/or the background encoder 1070 and combines the bits into an output stream or output file. The combiner component 1080 can include header information in the output file identifying or providing information such as encoding types, dictionaries and the like that can be used by a decoder to reconstruct the document image.
It is to be appreciated that the system and/or method of the present invention can be utilized in an overall segmented layered image system facilitating identification and/or compression of text, handwriting, drawings and the like. Further, those skilled in the art will recognize that the system and/or method of the present invention can be employed in a vast array of document image applications, including, but not limited to, photocopiers, document scanners, optical character recognition systems, PDAs, fax machines, digital cameras, tablet personal computers and/or digital video cameras.
In order to provide additional context for various aspects of the present invention,
With reference to
The system bus 1118 can be any of several types of bus structure(s) including the memory bus or memory controller, a peripheral bus or external bus, and/or a local bus using any variety of available bus architectures including, but not limited to, 11-bit bus, Industrial Standard Architecture (ISA), Micro-Channel Architecture (MSA), Extended ISA (EISA), Intelligent Drive Electronics (IDE), VESA Local Bus (VLB), Peripheral Component Interconnect (PCI), Universal Serial Bus (USB), Advanced Graphics Port (AGP), Personal Computer Memory Card International Association bus (PCMCIA), and Small Computer Systems Interface (SCSI).
The system memory 1116 includes volatile memory 1120 and nonvolatile memory 1122. The basic input/output system (BIOS), containing the basic routines to transfer information between elements within the computer 1112, such as during start-up, is stored in nonvolatile memory 1122. By way of illustration, and not limitation, nonvolatile memory 1122 can include read only memory (ROM), programmable ROM (PROM), electrically programmable ROM (EPROM), electrically erasable ROM (EEPROM), or flash memory. Volatile memory 1120 includes random access memory (RAM), which acts as external cache memory. By way of illustration and not limitation, RAM is available in many forms such as synchronous RAM (SRAM), dynamic RAM (DRAM), synchronous DRAM (SDRAM), double data rate SDRAM (DDR SDRAM), enhanced SDRAM (ESDRAM), Synchlink DRAM (SLDRAM), and direct Rambus RAM (DRRAM).
Computer 1112 also includes removable/nonremovable, volatile/nonvolatile computer storage media.
It is to be appreciated that
A user enters commands or information into the computer 1112 through input device(s) 1136. Input devices 1136 include, but are not limited to, a pointing device such as a mouse, trackball, stylus, touch pad, keyboard, microphone, joystick, game pad, satellite dish, scanner, TV tuner card, digital camera, digital video camera, web camera, and the like. These and other input devices connect to the processing unit 1114 through the system bus 1118 via interface port(s) 1138. Interface port(s) 1138 include, for example, a serial port, a parallel port, a game port, and a universal serial bus (USB). Output device(s) 1140 use some of the same type of ports as input device(s) 1136. Thus, for example, a USB port may be used to provide input to computer 1112, and to output information from computer 1112 to an output device 1140. Output adapter 1142 is provided to illustrate that there are some output devices 1140 like monitors, speakers, and printers among other output devices 1140 that require special adapters. The output adapters 1142 include, by way of illustration and not limitation, video and sound cards that provide a means of connection between the output device 1140 and the system bus 1118. It should be noted that other devices and/or systems of devices provide both input and output capabilities such as remote computer(s) 1144.
Computer 1112 can operate in a networked environment using logical connections to one or more remote computers, such as remote computer(s) 1144. The remote computer(s) 1144 can be a personal computer, a server, a router, a network PC, a workstation, a microprocessor based appliance, a peer device or other common network node and the like, and typically includes many or all of the elements described relative to computer 1112. For purposes of brevity, only a memory storage device 1146 is illustrated with remote computer(s) 1144. Remote computer(s) 1144 is logically connected to computer 1112 through a network interface 1148 and then physically connected via communication connection 1150. Network interface 1148 encompasses communication networks such as local-area networks (LAN) and wide-area networks (WAN). LAN technologies include Fiber Distributed Data Interface (FDDI), Copper Distributed Data Interface (CDDI), Ethernet/IEEE 1102.3, Token Ring/IEEE 1102.5 and the like. WAN technologies include, but are not limited to, point-to-point links, circuit switching networks like Integrated Services Digital Networks (ISDN) and variations thereon, packet switching networks, and Digital Subscriber Lines (DSL).
Communication connection(s) 1150 refers to the hardware/software employed to connect the network interface 1148 to the bus 1118. While communication connection 1150 is shown for illustrative clarity inside computer 1112, it can also be external to computer 1112. The hardware/software necessary for connection to the network interface 1148 includes, for exemplary purposes only, internal and external technologies such as, modems including regular telephone grade modems, cable modems and DSL modems, ISDN adapters, and Ethernet cards.
What has been described above includes examples of the present invention. It is, of course, not possible to describe every conceivable combination of components or methodologies for purposes of describing the present invention, but one of ordinary skill in the art may recognize that many further combinations and permutations of the present invention are possible. Accordingly, the present invention is intended to embrace all such alterations, modifications and variations that fall within the spirit and scope of the appended claims. Furthermore, to the extent that the term “includes” is used in either the detailed description or the claims, such term is intended to be inclusive in a manner similar to the term “comprising” as “comprising” is interpreted when employed as a transitional word in a claim.
|Cited Patent||Filing date||Publication date||Applicant||Title|
|US3606546||May 13, 1969||Sep 20, 1971||Dennison Mfg Co||Photocopier|
|US3719922||Jun 24, 1971||Mar 6, 1973||Lopes L||Digital camera|
|US3882454||Feb 2, 1973||May 6, 1975||Philips Corp||Methods of differentiating images and of recognizing shapes and characters, utilizing an optical image relay|
|US4606069||Jun 10, 1983||Aug 12, 1986||At&T Bell Laboratories||Apparatus and method for compression of facsimile information by pattern matching|
|US4747156||Jun 17, 1986||May 24, 1988||International Business Machines Corporation||Image preprocessing procedure for noise removal|
|US4754492||Jun 3, 1985||Jun 28, 1988||Picturetel Corporation||Method and system for adapting a digitized signal processing system for block processing with minimal blocking artifacts|
|US4922545||Feb 10, 1989||May 1, 1990||Kokusai Denshin Denwa Kabushiki Kaisha||Facsimile image encoding method|
|US4924494||May 5, 1989||May 8, 1990||Copam Electronics Corp.||Fax machine equipped for simultaneous transmission and reception via two telephone lines|
|US5077807||Feb 26, 1990||Dec 31, 1991||Palantir Corp.||Preprocessing means for use in a pattern classification system|
|US5129014||Dec 8, 1989||Jul 7, 1992||Xerox Corporation||Image registration|
|US5304991||May 26, 1992||Apr 19, 1994||Matsushita Electric Industrial Co., Ltd.||Selective call radio paging receiver having display function and reduced control inputs|
|US5402146||Oct 23, 1992||Mar 28, 1995||International Business Machines Corporation||System and method for video compression with artifact dispersion control|
|US5434953||Mar 20, 1992||Jul 18, 1995||Xerox Corporation||Use of fast textured reduction for discrimination of document image components|
|US5454047||Jan 12, 1994||Sep 26, 1995||Hughes Aircraft Company||Optical method and system for generating expansion coefficients for an image processing function|
|US5572565||Dec 30, 1994||Nov 5, 1996||Philips Electronics North America Corporation||Automatic segmentation, skinline and nipple detection in digital mammograms|
|US5572604||Nov 23, 1994||Nov 5, 1996||Lucent Technologies Inc.||Method for pattern recognition using prototype transformations and hierarchical filtering|
|US5592568 *||Feb 13, 1995||Jan 7, 1997||Xerox Corporation||Word spotting in bitmap images using context-sensitive character models without baselines|
|US5610996||Jul 13, 1994||Mar 11, 1997||Microsoft Corporation||Method and apparatus for arc segmentation in handwriting recognition|
|US5689585 *||Apr 28, 1995||Nov 18, 1997||Xerox Corporation||Method for aligning a text image to a transcription of the image|
|US5737455||Dec 12, 1994||Apr 7, 1998||Xerox Corporation||Antialiasing with grey masking techniques|
|US5754183 *||May 6, 1996||May 19, 1998||Cambridge Animation Systems Limited||Image processing apparatus and method for producing pixel data in dependence upon the shape of a sectional line extending between boundary lines of an object|
|US5778092||Dec 20, 1996||Jul 7, 1998||Xerox Corporation||Method and apparatus for compressing color or gray scale documents|
|US5790696||Feb 20, 1996||Aug 4, 1998||International Business Machines Corporation||Image segmentation apparatus and a character recognition apparatus|
|US5805727||Dec 5, 1995||Sep 8, 1998||International Business Machines Corporation||Image recognition method and apparatus|
|US5805739||Apr 2, 1996||Sep 8, 1998||Picturetel Corporation||Lapped orthogonal vector quantization|
|US5828771||Dec 15, 1995||Oct 27, 1998||Xerox Corporation||Method and article of manufacture for determining whether a scanned image is an original image or fax image|
|US5883986 *||Jun 2, 1995||Mar 16, 1999||Xerox Corporation||Method and system for automatic transcription correction|
|US5910805 *||Jan 11, 1996||Jun 8, 1999||Oclc Online Computer Library Center||Method for displaying bitmap derived text at a display having limited pixel-to-pixel spacing resolution|
|US5914748||Aug 30, 1996||Jun 22, 1999||Eastman Kodak Company||Method and apparatus for generating a composite image using the difference of two images|
|US5915044||Apr 13, 1998||Jun 22, 1999||Intel Corporation||Encoding video images using foreground/background segmentation|
|US5917951||Oct 3, 1997||Jun 29, 1999||International Business Machines Corporation||Clustered aperiodic mask|
|US5917964||Dec 23, 1996||Jun 29, 1999||Lg Electronics, Inc.||Method and apparatus for pre-processing image data of encoders|
|US5923380||Jan 25, 1996||Jul 13, 1999||Polaroid Corporation||Method for replacing the background of an image|
|US5930377||May 7, 1998||Jul 27, 1999||Digimarc Corporation||Method for image encoding|
|US5960111||Feb 10, 1997||Sep 28, 1999||At&T Corp||Method and apparatus for segmenting images prior to coding|
|US5960119||Aug 28, 1996||Sep 28, 1999||International Business Machines Corporation||Method of and system for encoding digital images|
|US5991515||Jul 15, 1997||Nov 23, 1999||Adobe Systems Incorporated||Method and apparatus for compressing and decompressing data prior to display|
|US6000124||Apr 25, 1997||Dec 14, 1999||Seiko Precision Inc.||Method and apparatus for manufacturing multilayer printed circuit board|
|US6020972||Nov 14, 1997||Feb 1, 2000||Xerox Corporation||System for performing collective symbol-based compression of a corpus of document images|
|US6029126||Jun 30, 1998||Feb 22, 2000||Microsoft Corporation||Scalable audio coder and decoder|
|US6058362||Jun 30, 1998||May 2, 2000||Microsoft Corporation||System and method for masking quantization noise of audio signals|
|US6064762||Jun 6, 1995||May 16, 2000||International Business Machines Corporation||System and method for separating foreground information from background information on a document|
|US6069636 *||Oct 15, 1996||May 30, 2000||Fuji Xerox Co., Ltd.||Embedding information into images by varying pixel parameters|
|US6072496||Jun 8, 1998||Jun 6, 2000||Microsoft Corporation||Method and system for capturing and representing 3D geometry, color and shading of facial expressions and other animated objects|
|US6073153||Jun 3, 1998||Jun 6, 2000||Microsoft Corporation||Fast system and method for computing modulated lapped transforms|
|US6094506||Oct 25, 1995||Jul 25, 2000||Microsoft Corporation||Automatic generation of probability tables for handwriting recognition systems|
|US6100825||Dec 31, 1998||Aug 8, 2000||Microsoft Corporation||Cluster-based data compression system and method|
|US6108444 *||Sep 29, 1997||Aug 22, 2000||Xerox Corporation||Method of grouping handwritten word segments in handwritten document images|
|US6108446||Feb 18, 1997||Aug 22, 2000||Hoshen; Joseph||Method and apparatus for extracting cluster shape features from digital images|
|US6115689||May 27, 1998||Sep 5, 2000||Microsoft Corporation||Scalable audio coder and decoder|
|US6118890||Nov 12, 1997||Sep 12, 2000||International Business Machines Corporation||System and method for broad classification of biometric patterns|
|US6137908||Jun 29, 1994||Oct 24, 2000||Microsoft Corporation||Handwriting recognition system simultaneously considering shape and context information|
|US6144767||Nov 10, 1998||Nov 7, 2000||At&T Corp||Efficient convolutions using polynomial covers|
|US6151424||Sep 9, 1996||Nov 21, 2000||Hsu; Shin-Yi||System for identifying objects and features in an image|
|US6154762||Jun 3, 1998||Nov 28, 2000||Microsoft Corporation||Fast system and method for computing modulated lapped transforms|
|US6182034||Jun 30, 1998||Jan 30, 2001||Microsoft Corporation||System and method for producing a fixed effort quantization step size with a binary search|
|US6192360||Jun 23, 1998||Feb 20, 2001||Microsoft Corporation||Methods and apparatus for classifying text and for building a text classifier|
|US6233364||Sep 18, 1998||May 15, 2001||Dainippon Screen Engineering Of America Incorporated||Method and system for detecting and tagging dust and scratches in a digital image|
|US6240380||Jun 30, 1998||May 29, 2001||Microsoft Corporation||System and method for partially whitening and quantizing weighting functions of audio signals|
|US6253165||Jun 30, 1998||Jun 26, 2001||Microsoft Corporation||System and method for modeling probability distribution functions of transform coefficients of encoded signal|
|US6256608||Jun 30, 1998||Jul 3, 2001||Microsoa Corporation||System and method for entropy encoding quantized transform coefficients of a signal|
|US6272253||Oct 25, 1996||Aug 7, 2001||Texas Instruments Incorporated||Content-based video compression|
|US6285801||May 29, 1998||Sep 4, 2001||Stmicroelectronics, Inc.||Non-linear adaptive image filter for filtering noise such as blocking artifacts|
|US6295371 *||Oct 22, 1998||Sep 25, 2001||Xerox Corporation||Method and apparatus for image processing employing image segmentation using tokenization|
|US6309424||Nov 3, 2000||Oct 30, 2001||Realtime Data Llc||Content independent data compression method and system|
|US6310972||Jun 27, 1997||Oct 30, 2001||Competitive Technologies Of Pa, Inc.||Shape adaptive technique for image and video compression|
|US6321243||Jun 27, 1997||Nov 20, 2001||Microsoft Corporation||Laying out a paragraph by defining all the characters as a single text run by substituting, and then positioning the glyphs|
|US6324560||May 2, 2000||Nov 27, 2001||Microsoft Corporation||Fast system and method for computing modulated lapped transforms|
|US6326977||Nov 3, 1998||Dec 4, 2001||Sharp Laboratories Of America, Inc.||Rendering of YCBCR images on an RGS display device|
|US6334001||Dec 7, 2000||Dec 25, 2001||Xerox Corporation||Iterative smoothing technique for pre-processing mixed raster content planes to improve the quality of a decompressed image and increase document compression ratios|
|US6345119||Feb 18, 1997||Feb 5, 2002||Fujitsu Limited||Handwritten character recognition apparatus and method using a clustering algorithm|
|US6411733 *||Nov 25, 1998||Jun 25, 2002||Xerox Corporation||Method and apparatus for separating document image object types|
|US6564263 *||Dec 3, 1999||May 13, 2003||International Business Machines Corporation||Multimedia content description framework|
|US6633670||Mar 31, 2000||Oct 14, 2003||Sharp Laboratories Of America, Inc.||Mask generation for multi-layer image decomposition|
|US6658151 *||Apr 8, 1999||Dec 2, 2003||Ricoh Co., Ltd.||Extracting information from symbolically compressed document images|
|US6731800||Dec 8, 1999||May 4, 2004||Algo Vision Lura Tech Gmbh||Method for compressing scanned, colored and gray-scaled documents|
|US6735335 *||May 30, 2000||May 11, 2004||Microsoft Corporation||Method and apparatus for discriminating between documents in batch scanned document files|
|US6738079 *||Jun 2, 2000||May 18, 2004||Sun Microsystems, Inc.||Graphical user interface layout customizer|
|US6819796||Dec 26, 2000||Nov 16, 2004||Sharp Kabushiki Kaisha||Method of and apparatus for segmenting a pixellated image|
|US6826727 *||Nov 24, 1999||Nov 30, 2004||Bitstream Inc.||Apparatus, methods, programming for automatically laying out documents|
|US6901153||Mar 14, 1996||May 31, 2005||Ati Technologies Inc.||Hybrid software/hardware video decoder for personal computer|
|US6907141||Nov 21, 2000||Jun 14, 2005||Fuji Xerox Co., Ltd.||Image data sorting device and image data sorting method|
|US6941014 *||Dec 15, 2000||Sep 6, 2005||Xerox Corporation||Method and apparatus for segmenting an image using a combination of image segmentation techniques|
|US6977664||Sep 21, 2000||Dec 20, 2005||Nippon Telegraph And Telephone Corporation||Method for separating background sprite and foreground object and method for extracting segmentation mask and the apparatus|
|US7039232 *||Jun 14, 2002||May 2, 2006||Xerox Corporation||Block level analysis of segmentation tags|
|US20010004618 *||Dec 11, 2000||Jun 21, 2001||Kyung-Seon Hur||Anti-rollback system for automatic transmission and method thereof|
|US20020064313||Nov 29, 2000||May 30, 2002||Xerox Corporation||Rate-distortion optimization system and method for image compression|
|US20030123729||Dec 31, 2001||Jul 3, 2003||Debargha Mukherjee||Coder matched layer separation for compression of compound documents|
|US20030133615 *||Jan 16, 2002||Jul 17, 2003||Xerox Corporation||Method and apparatus for improving image appearance|
|US20030198386 *||Apr 19, 2002||Oct 23, 2003||Huitao Luo||System and method for identifying and extracting character strings from captured image data|
|US20030229856 *||Feb 12, 2001||Dec 11, 2003||Lynn Heath A.||Text grid creation tools|
|EP0567344A2||Apr 23, 1993||Oct 27, 1993||Canon Kabushiki Kaisha||Method and apparatus for character recognition|
|EP0621554A2||Apr 18, 1994||Oct 26, 1994||Xerox Corporation||Method and apparatus for automatic determination of text line, word and character cell spatial features|
|EP0802680A2||Apr 7, 1997||Oct 22, 1997||Philips Patentverwaltung GmbH||Image segmentation method|
|EP0853421A2||Jan 13, 1998||Jul 15, 1998||Nec Corporation||Method and apparatus for pattern matching encoding|
|EP1006714A2||Nov 29, 1999||Jun 7, 2000||Xerox Corporation||Method of processing mixed raster content planes|
|EP1104916A1||Dec 4, 1999||Jun 6, 2001||Luratech Gesellschaft für Luft-und Raumfahrt-Technologie & Multimedia mbH||Method for compressing color and/or grey-level scanned documents|
|EP1146478A2||Mar 22, 2001||Oct 17, 2001||Matsushita Electrical Ind. Co.||A method for extracting titles from digital images|
|GB2181875A||Title not available|
|GB2230633A||Title not available|
|1||Cosman, et al. "Memory Efficient Quadtree Wavelet Coding for Compound Images" Conference Record of the Thirty-Third Asilomar Conference (Oct. 24-27, 1999) Piscataway, New Jersey, pp. 1173-1177.|
|2||Debargha Mukherjee, et al.; "JPEG2000-Matched MRC Compression of Compound Documents"; Jun. 6, 2002.|
|3||European Search Report dated Nov. 21, 2005, mailed Nov. 30, 2005, for European Patent Application Serial No. EP 03 00 6769, 3 Pages.|
|4||European Search Report dated Oct. 4, 2005 mailed Oct. 13, 2005 for PCT U.S. Appl. No. 03/005,431, 5 pages.|
|5||European Search Report dated Oct. 4, 2005 mailed Oct. 13, 2005 for PCT U.S. Appl. No. 10/180,169, 5 pages.|
|6||European Search Report dated Sep. 15, 2005, mailed Sep. 30, 2005, for European Patent Application Serial No. EP 03 00 5429, 4 Pages.|
|7||Felix Balado Pumarino, et al.; "A Two-Stage Codebook Building Method Using Fast WAN"; University of Vigo, Communications Technology Department.|
|8||Guotong Feng, et al.; "High Quality MRC Document Coding"; School of Electrical and Computer Engineering; Purdue University; Sarnoff Corporation.|
|9||Haffner, et al. "Browsing through high quality documents images with DjVu" Research and Technology Advances in Digital Libraries. ADL 1998 Proceedings (Apr. 22, 1998) IEEE International Forum in Santa Barabra, California, pp. 309-318.|
|10||Henrique S. Malvar; "Fast Progressive Wavelet Coding"; Microsoft Research.|
|11||Leon Bottou, et al.; "High Quality Document Image Compression with DjVu"; Jul. 13, 1998; AT&T Labs.|
|12||Mukherjee, et al. "LPEG-Matched MRC Compression of Compound Documents" Proceedings 2001 International Conference of Image Processing (Oct. 7-10, 2001) Thessalonki, Greece, pp. 434-437.|
|13||Patrice Y. Simard, et al.; "A Wavelet Coder for Masked Images"; Proceedings of the Data Compression Conference (DCC'01); Microsoft Research.|
|14||Patrice Y. Simard, et al.; "Boxlets: A Fast Convolution Algorithm for Signal Processing and Neural Networks"; AT&T Labs-Research.|
|15||Patrick Haffner, et al.; "Color Documents on the Web with DjVu"; AT&T Labs-Research.|
|16||Patrick Haffner, et al.; "DjVu: Analyzing and Compressing Scanned Documents for Internet Distribution"; AT&T Labs-Research; pp. 1-4.|
|17||Ping Wah Wong; Halftoning by Multiscale Dot Distribution; Proceedings of the '95 Int' l. Conf. on Image Processing (ICIP '95); pp. 117-120.|
|18||Qian Huang el al.; "Foreground/Background Segmentation of Color Images by Integration of Multiple Cues"; Proceedings of '95 Int'l. Conf. on Image Processing (ICIP.|
|19||Queiroz, et al. "Optimizing Block-Threseholding Segmentation for Multilayer Compression of Compound Images" (Sep. 9, 2000) IEEE Transactions on Image Processing, IEEE Inc. New York, pp. 1461-1471.|
|20||Rangachar Kasturi, et al.; "Document Image Analysis: A Primer" ; Sadhana vol. 27, Part 1, Feb. 2002, pp. 3-22.|
|21||Salembier, et al. "Region-Based Representations of Image and Video: Segmentation Tools for Multimedia Services" (Dec. 8, 1999) IEEE Transactions on Circuits and Systems for Video Technology, IEEE Inc. New York, pp. 1147-1169.|
|22||Simard, et al. " A Forefround/Background Separation Algorith for Image Compression" (Mar. 23, 2004) Data Compression Conference, Snowbird, Utah, pp. 498-507.|
|23||Simard, et al. "A Wavelet Coder for Masked Images" Proceedings IEE Data Compression Conference (Mar. 27, 2001) Snowbird, Utah, pp. 93-102.|
|24||Trevor Hastie, et al.; "Metrics and Models for Handwritten Character Recognition"; Dec. 8, 1997; pp. 1-18.|
|25||U.S. Appl. No. 10/133,842, filed Apr. 25, 2002, Simard et al.|
|26||U.S. Appl. No. 11/198,562, filed Aug. 5, 2005, Simard et al.|
|27||U.S. Appl. No. 11/286,622, filed Nov. 23, 2005, Malvar et al.|
|28||Witten, Ian H., et al; "Textual Image Compression", Data Compression Conference, IEEE, 10 pages, Mar. 24, 1992.|
|29||Yann LeCun, et al.; "Learning Algorithms for Classification: A Comparison on Handwritten Digit Recongition"; AT&T Bell Laboratories.|
|30||Yiu-fai Wong, et al.; Preprocessing of Video Signals for MPEG Coding by Clustering Filter; Proceedings of the '95 Int'l. Conf. on Image Processing (ICIP '95); pp. 129-132.|
|Citing Patent||Filing date||Publication date||Applicant||Title|
|US7715635 *||Sep 28, 2006||May 11, 2010||Amazon Technologies, Inc.||Identifying similarly formed paragraphs in scanned images|
|US7788580||Mar 28, 2006||Aug 31, 2010||Amazon Technologies, Inc.||Processing digital images including headers and footers into reflow content|
|US7810026||Sep 29, 2006||Oct 5, 2010||Amazon Technologies, Inc.||Optimizing typographical content for transmission and display|
|US7961987||Jul 3, 2008||Jun 14, 2011||Amazon Technologies, Inc.||Efficient processing of non-reflow content in a digital image|
|US7966557||Mar 29, 2006||Jun 21, 2011||Amazon Technologies, Inc.||Generating image-based reflowable files for rendering on various sized displays|
|US8023738||Mar 28, 2006||Sep 20, 2011||Amazon Technologies, Inc.||Generating reflow files from digital images for rendering on various sized displays|
|US8413048||Jun 9, 2010||Apr 2, 2013||Amazon Technologies, Inc.||Processing digital images including headers and footers into reflow content|
|US8499236||Jan 21, 2010||Jul 30, 2013||Amazon Technologies, Inc.||Systems and methods for presenting reflowable content on a display|
|US8566707||Jun 20, 2011||Oct 22, 2013||Amazon Technologies, Inc.||Generating image-based reflowable files for rendering on various sized displays|
|US8572480||Sep 30, 2008||Oct 29, 2013||Amazon Technologies, Inc.||Editing the sequential flow of a page|
|US8782516||Dec 21, 2007||Jul 15, 2014||Amazon Technologies, Inc.||Content style detection|
|U.S. Classification||715/243, 715/255|
|International Classification||G06F17/00, G06K9/20|
|Apr 25, 2002||AS||Assignment|
Owner name: MICROSOFT CORPORATION, WASHINGTON
Free format text: ASSIGNMENT OF ASSIGNORS INTEREST;ASSIGNORS:SIMARD, PATRICE Y.;RINKER, JAMES RUSSELL;REEL/FRAME:012859/0205
Effective date: 20020425
|Sep 20, 2011||FPAY||Fee payment|
Year of fee payment: 4
|Dec 9, 2014||AS||Assignment|
Owner name: MICROSOFT TECHNOLOGY LICENSING, LLC, WASHINGTON
Free format text: ASSIGNMENT OF ASSIGNORS INTEREST;ASSIGNOR:MICROSOFT CORPORATION;REEL/FRAME:034541/0477
Effective date: 20141014